提交 b7a4772f 编写于 作者: J JiabinYang

refine doc

上级 84711d9d
......@@ -32,9 +32,11 @@ python preprocess.py --data_path ./data/1-billion-word-language-modeling-benchma
### 单机训练:
```bash
export CPU_NUM=1
python train.py \
--train_data_path ./data/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled \
--dict_path data/1-billion_dict \
--with_hs --with_nce --is_local \
2>&1 | tee train.log
```
......
......@@ -32,9 +32,11 @@ The command line options for training can be listed by `python train.py -h`.
### Local Train:
```bash
export CPU_NUM=1
python train.py \
--train_data_path ./data/1-billion-word-language-modeling-benchmark-r13output/training-monolingual.tokenized.shuffled \
--dict_path data/1-billion_dict \
--with_hs --with_nce --is_local \
2>&1 | tee train.log
```
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册